Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
paddle_dbnet
Commits
5cab4c0c
Unverified
Commit
5cab4c0c
authored
May 17, 2022
by
lgcy
Committed by
GitHub
May 17, 2022
Browse files
update lmdb_dateset for ppocrv3 rec
对lmdb_dataset适配ppocrv3的RecConAug数据增强
parent
40db742e
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
24 additions
and
0 deletions
+24
-0
ppocr/data/lmdb_dataset.py
ppocr/data/lmdb_dataset.py
+24
-0
No files found.
ppocr/data/lmdb_dataset.py
View file @
5cab4c0c
...
@@ -88,6 +88,29 @@ class LMDBDataSet(Dataset):
...
@@ -88,6 +88,29 @@ class LMDBDataSet(Dataset):
if
imgori
is
None
:
if
imgori
is
None
:
return
None
return
None
return
imgori
return
imgori
def
get_ext_data
(
self
):
ext_data_num
=
0
for
op
in
self
.
ops
:
if
hasattr
(
op
,
'ext_data_num'
):
ext_data_num
=
getattr
(
op
,
'ext_data_num'
)
break
load_data_ops
=
self
.
ops
[:
self
.
ext_op_transform_idx
]
ext_data
=
[]
while
len
(
ext_data
)
<
ext_data_num
:
lmdb_idx
,
file_idx
=
self
.
data_idx_order_list
[
np
.
random
.
randint
(
self
.
__len__
())]
lmdb_idx
=
int
(
lmdb_idx
)
file_idx
=
int
(
file_idx
)
sample_info
=
self
.
get_lmdb_sample_info
(
self
.
lmdb_sets
[
lmdb_idx
][
'txn'
],
file_idx
)
if
sample_info
is
None
:
continue
img
,
label
=
sample_info
data
=
{
'image'
:
img
,
'label'
:
label
}
outs
=
transform
(
data
,
load_data_ops
)
ext_data
.
append
(
data
)
return
ext_data
def
get_lmdb_sample_info
(
self
,
txn
,
index
):
def
get_lmdb_sample_info
(
self
,
txn
,
index
):
label_key
=
'label-%09d'
.
encode
()
%
index
label_key
=
'label-%09d'
.
encode
()
%
index
...
@@ -109,6 +132,7 @@ class LMDBDataSet(Dataset):
...
@@ -109,6 +132,7 @@ class LMDBDataSet(Dataset):
return
self
.
__getitem__
(
np
.
random
.
randint
(
self
.
__len__
()))
return
self
.
__getitem__
(
np
.
random
.
randint
(
self
.
__len__
()))
img
,
label
=
sample_info
img
,
label
=
sample_info
data
=
{
'image'
:
img
,
'label'
:
label
}
data
=
{
'image'
:
img
,
'label'
:
label
}
data
[
'ext_data'
]
=
self
.
get_ext_data
()
outs
=
transform
(
data
,
self
.
ops
)
outs
=
transform
(
data
,
self
.
ops
)
if
outs
is
None
:
if
outs
is
None
:
return
self
.
__getitem__
(
np
.
random
.
randint
(
self
.
__len__
()))
return
self
.
__getitem__
(
np
.
random
.
randint
(
self
.
__len__
()))
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment